[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-PostHog-creating-experiments-de":3,"guides-for-PostHog-creating-experiments":1642,"similar-k17erc36epeh2pmf9zgrfhe19s86ne9f-de":1643},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":244,"isFallback":226,"parentExtension":248,"providers":249,"relations":254,"repo":256,"tags":1639,"workflow":1640},1778695660274.5056,"k17erc36epeh2pmf9zgrfhe19s86ne9f",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions to configuring-experiment-rollout and metric setup to configuring-experiment-analytics.\nTRIGGER when: user asks to create a new experiment or A/B test, OR when you are about to call experiment-create.\nDO NOT TRIGGER when: user is updating an existing experiment, managing lifecycle, or only browsing experiments.",{"claudeCode":12},"PostHog/posthog","creating-experiments","https://github.com/PostHog/posthog",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":242},1778697075518.117,"kn759674w9fcfkwfqsqvzpwpbh86n4wm","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":201,"promptVersionExtension":206,"promptVersionScoring":207,"purpose":208,"rationale":209,"score":210,"summary":211,"tags":212,"targetMarket":218,"tier":219,"useCases":220},[21,26,29,32,36,39,43,47,50,53,57,61,65,69,72,75,78,81,84,87,91,95,100,104,108,111,114,117,121,124,127,130,133,136,139,143,147,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of guiding agents through the experiment creation flow, specifying the steps and triggers.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a structured 3-step process for experiment creation, delegating to other specific skills, which goes beyond default LLM behavior and provides a clear value for creating A/B tests.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill covers the complete lifecycle of experiment creation, including defining hypotheses, configuring rollouts, and setting up analytics, and delegates detailed configuration to other skills, indicating readiness for real workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses solely on the experiment creation flow, delegating configuration details to other specific skills, adhering to a single responsibility.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The provided description accurately reflects the skill's functionality, detailing the 3-step process, triggers, and non-goals.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill utilizes specific tools like `experiment-create`, `configuring-experiment-rollout`, and `configuring-experiment-analytics`, adhering to narrow verb-noun actions.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md provides a clear JSON structure for the `experiment-create` call, detailing parameters like name, feature_flag_key, description, and parameters, including default values and variant splits.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The tool names used (`experiment-create`, `configuring-experiment-rollout`, `configuring-experiment-analytics`) are descriptive and specific to the domain.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The `experiment-create` tool schema specifies necessary parameters like name and feature_flag_key, and the workflow clearly states that metrics are configured *after* creation, indicating minimal input requirements.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The repository includes a LICENSE file with the MIT Expat license, which is a permissive open-source license.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The last commit was on 2026-05-13, which is within the last 90 days, indicating recent maintenance.",{"category":58,"check":62,"severity":63,"summary":64},"Dependency Management","not_applicable","The skill does not appear to use third-party dependencies that would require explicit management or updating beyond what's bundled by the Claude Code environment.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill does not appear to handle or expose secrets, relying on external tool invocations which are assumed to manage their own authentication.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill operates on structured inputs and delegates to tools, with no indication of loading untrusted external data as instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill does not fetch external code or data at runtime; all operations are within the bundled scripts and tool calls.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill operates within the Claude Code environment and its tool calls are assumed to be sandboxed, with no indication of file system manipulation outside its scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","There is no evidence of detached processes or retry loops around denied tool calls in the skill's logic.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill does not instruct the agent to read or submit confidential data; outbound calls are to documented PostHog tools.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled SKILL.md and other prose files do not contain hidden text tricks or steering characters.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's logic is presented as readable Markdown and does not involve obfuscated code, base64 payloads, or runtime script fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill operates by calling specific tools and does not make assumptions about the user's project file structure.",{"category":96,"check":97,"severity":98,"summary":99},"Trust","Issues Attention","warning","There are 544 open issues and 163 closed issues in the last 90 days, indicating a low closure rate (approx. 23%) and a significant number of unaddressed issues.",{"category":101,"check":102,"severity":24,"summary":103},"Versioning","Release Management","The repository has a recent commit date and a CHANGELOG.md, indicating a managed release process.",{"category":105,"check":106,"severity":24,"summary":107},"Code Execution","Validation","The skill relies on the underlying tool schemas for validation, and its own logic processes structured inputs, implying validation is handled at the tool level.",{"category":66,"check":109,"severity":24,"summary":110},"Unguarded Destructive Operations","The skill's primary action is creating an experiment, which is not a destructive operation in the context of file system or infrastructure changes, and its delegated tools are assumed to handle confirmations if necessary.",{"category":105,"check":112,"severity":24,"summary":113},"Error Handling","The skill delegates error handling to the called tools and their underlying APIs, which are expected to return structured error messages.",{"category":105,"check":115,"severity":63,"summary":116},"Logging","The skill itself does not perform destructive actions or outbound calls directly; logging is handled by the underlying tools and the Claude Code environment.",{"category":118,"check":119,"severity":63,"summary":120},"Compliance","GDPR","The skill does not handle personal data; it deals with experiment configuration which is not typically PII.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The skill's functionality is general to experiment creation and does not exhibit any regional or jurisdictional limitations, therefore its target market is global.",{"category":92,"check":125,"severity":24,"summary":126},"Runtime stability","The skill relies on standard Claude Code environment tools and does not appear to have OS-specific assumptions.",{"category":44,"check":128,"severity":24,"summary":129},"README","The README file provides a comprehensive overview of PostHog's features and setup instructions.",{"category":33,"check":131,"severity":24,"summary":132},"Tool surface size","This skill directly exposes only one primary tool (`experiment-create`) and delegates to others, keeping the surface area focused.",{"category":40,"check":134,"severity":24,"summary":135},"Overlapping near-synonym tools","The skill does not expose overlapping near-synonym tools; it delegates to clearly defined, distinct tools for specific functions.",{"category":44,"check":137,"severity":24,"summary":138},"Phantom features","All advertised features related to experiment creation are implemented and delegated to the relevant tools within the PostHog ecosystem.",{"category":140,"check":141,"severity":63,"summary":142},"Install","Installation instruction","This skill is part of the Claude Code environment and does not require separate installation instructions.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","The skill relies on the underlying tools for error reporting, which are expected to provide actionable messages.",{"category":148,"check":149,"severity":63,"summary":150},"Execution","Pinned dependencies","The skill operates within the Claude Code environment and does not manage external dependencies directly.",{"category":33,"check":152,"severity":63,"summary":153},"Dry-run preview","Experiment creation is a state-changing operation, but the skill does not expose a direct dry-run capability; this is assumed to be handled by the underlying PostHog API or CLI if available.",{"category":155,"check":156,"severity":24,"summary":157},"Protocol","Idempotent retry & timeouts","The skill delegates its operations to PostHog tools, which are assumed to implement appropriate timeouts and idempotency where applicable.",{"category":118,"check":159,"severity":24,"summary":160},"Telemetry opt-in","The skill does not emit telemetry; this functionality is managed by the underlying PostHog platform and Claude Code environment.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The description clearly defines the purpose as guiding experiment creation through a 3-step flow and specifies precise triggers and exclusions.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the skill's core capability and trigger conditions.",{"category":44,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md content is well-structured and avoids unnecessary verbosity, keeping the core instructions clear.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","The SKILL.md outlines the high-level steps and delegates detailed configuration to other skills, demonstrating progressive disclosure.",{"category":171,"check":175,"severity":63,"summary":176},"Forked exploration","This skill focuses on a direct creation workflow and does not involve deep exploration or code review that would necessitate forked context.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","The SKILL.md provides a concrete JSON example for the `experiment-create` call, demonstrating the required structure and parameters.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The SKILL.md documents edge cases like the distinction between `split_percent` and `rollout_percentage`, and the handling of different experiment types.",{"category":105,"check":184,"severity":63,"summary":185},"Tool Fallback","The skill uses tools inherent to the Claude Code environment and does not have external MCP dependencies with fallbacks.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The skill's logic implies that it would halt if prerequisite information for experiment creation is missing or invalid, and it delegates to tools that are expected to report errors.",{"category":92,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill clearly defines its scope and delegates to other specific skills (`configuring-experiment-rollout`, `configuring-experiment-analytics`) explicitly, avoiding implicit coupling.",1778697075131,"This skill guides users through creating A/B tests in PostHog by defining hypotheses, configuring rollouts, and setting up analytics. It orchestrates calls to other specific skills for detailed configuration and uses the `experiment-create` tool.",[196,197,198,199,200],"Guides through 3-step experiment creation flow","Delegates rollout configuration to `configuring-experiment-rollout`","Delegates analytics setup to `configuring-experiment-analytics`","Creates experiment drafts quickly","Supports specifying experiment name, hypothesis, and feature flag key",[202,203,204,205],"Updating an existing experiment","Managing experiment lifecycle (beyond creation)","Only browsing existing experiments","Configuring metrics directly during creation","3.0.0","4.4.0","To streamline the creation of A/B tests in PostHog by providing a structured, step-by-step process for defining experiments and their configurations.","The primary factor lowering the score is the high number of open issues relative to closed issues, indicating potential maintenance concerns. Additionally, the absence of a dry-run preview for the state-changing operation was noted.",79,"A well-documented skill for guided experiment creation, though maintenance could be improved.",[213,214,215,216,217],"experiments","ab-testing","product-analytics","posthog","feature-flags","global","community",[221,222,223],"When a user asks to create a new experiment or A/B test","When preparing to call the `experiment-create` tool","To quickly create a draft experiment for later refinement",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"popularity":237,"security":238,"testCoverage":241},{"hasLockfile":226},true,1778697058990,{"descriptionLength":229,"readmeSize":230},471,10694,{"closedIssues90d":232,"forks":233,"hasChangelog":226,"openIssues90d":234,"pushedAt":235,"stars":236},163,2714,544,1778695622000,34459,{"npmDownloads":8},{"hasNpmPackage":226,"license":239,"smitheryVerified":240},"NOASSERTION",false,{"hasCi":240,"hasTests":226},{"updatedAt":243},1778697075518,{"basePath":245,"githubOwner":246,"githubRepo":216,"locale":18,"slug":13,"type":247},"products/experiments/skills/creating-experiments","PostHog","skill",null,{"evaluate":250,"extract":252},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":251,"targetMarket":218,"tier":219},[213,214,215,216,217],{"commitSha":253},"HEAD",{"repoId":255},"kd7f22zf7qb3eschtk9s2qdv4586mfts",{"_creationTime":257,"_id":255,"identity":258,"providers":259,"workflow":1634},1778695623992.2551,{"githubOwner":246,"githubRepo":216,"sourceUrl":14},{"classify":260,"discover":1613,"extract":1616,"github":1618,"npm":1633},{"commitSha":253,"extensions":261},[262,274,282,290,298,306,314,322,330,338,346,354,362,370,378,386,393,401,409,417,425,433,440,448,456,464,471,478,486,494,502,510,517,525,533,541,548,556,564,571,579,593,605,613,621,629,637,645,653,661,669,685,693,703,717,735,745,754,762,774,782,790,798,806,814,822,830,838,846,854,864,872,880,888,900,910,915,923,931,939,947,955,966,986,994,1020,1028,1036,1044,1058,1076,1084,1192,1204,1234,1244,1254,1268,1276,1284,1292,1300,1308,1316,1324,1332,1340,1348,1356,1364,1375,1387,1399,1408,1417,1426,1435,1445,1453,1462,1472,1481,1492,1501,1510,1519,1528,1538,1548,1559,1569,1579,1589,1604],{"basePath":263,"description":264,"displayName":265,"installMethods":266,"rationale":267,"selectedPaths":268,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/customerio","Send event data and emails into Customer.io.","Customer.io",{"claudeCode":265},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/customerio/plugin.json",[269],{"path":270,"priority":271},"plugin.json","mandatory","rule","plugin",{"basePath":275,"description":276,"displayName":277,"installMethods":278,"rationale":279,"selectedPaths":280,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/hubspot","Send contact data to Hubspot on PostHog identify events.","Hubspot",{"claudeCode":277},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/hubspot/plugin.json",[281],{"path":270,"priority":271},{"basePath":283,"description":284,"displayName":285,"installMethods":286,"rationale":287,"selectedPaths":288,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/intercom","Send event data to Intercom on PostHog events.","Intercom",{"claudeCode":285},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/intercom/plugin.json",[289],{"path":270,"priority":271},{"basePath":291,"description":292,"displayName":293,"installMethods":294,"rationale":295,"selectedPaths":296,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/pace-posthog-integration","Pace is a tool that equips sellers with relevant insights at the right time so they can spend time growing revenue. It allows them to convert, retain, and grow customers by prioritizing time and effort on the users who need it most.","Pace Integration",{"claudeCode":293},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/pace-posthog-integration/plugin.json",[297],{"path":270,"priority":271},{"basePath":299,"description":300,"displayName":301,"installMethods":302,"rationale":303,"selectedPaths":304,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/posthog-avo","Export PostHog events to Avo inspector.","Avo Inspector Plugin",{"claudeCode":301},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/posthog-avo/plugin.json",[305],{"path":270,"priority":271},{"basePath":307,"description":308,"displayName":309,"installMethods":310,"rationale":311,"selectedPaths":312,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/posthog-braze-app","Import analytics from Braze and export PostHog events to Braze.","Braze",{"claudeCode":309},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/posthog-braze-app/plugin.json",[313],{"path":270,"priority":271},{"basePath":315,"description":316,"displayName":317,"installMethods":318,"rationale":319,"selectedPaths":320,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/posthog-engage-so","Send user and event data to Engage for personalized  engagement.","Engage",{"claudeCode":317},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/posthog-engage-so/plugin.json",[321],{"path":270,"priority":271},{"basePath":323,"description":324,"displayName":325,"installMethods":326,"rationale":327,"selectedPaths":328,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/posthog-gcs","Sends events to GCS on ingestion.","GCS Export",{"claudeCode":325},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/posthog-gcs/plugin.json",[329],{"path":270,"priority":271},{"basePath":331,"description":332,"displayName":333,"installMethods":334,"rationale":335,"selectedPaths":336,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/posthog-laudspeaker-app","Send event data to Laudspeaker","Laudspeaker",{"claudeCode":333},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/posthog-laudspeaker-app/plugin.json",[337],{"path":270,"priority":271},{"basePath":339,"description":340,"displayName":341,"installMethods":342,"rationale":343,"selectedPaths":344,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/posthog-patterns-app","Send events data to Patterns App","Patterns App",{"claudeCode":341},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/posthog-patterns-app/plugin.json",[345],{"path":270,"priority":271},{"basePath":347,"description":348,"displayName":349,"installMethods":350,"rationale":351,"selectedPaths":352,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/posthog-plugin-replicator","Replicate PostHog event stream in another PostHog instance","Replicator",{"claudeCode":349},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/posthog-plugin-replicator/plugin.json",[353],{"path":270,"priority":271},{"basePath":355,"description":356,"displayName":357,"installMethods":358,"rationale":359,"selectedPaths":360,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/pubsub","Sends events to a Pub/Sub topic on ingestion.","Pub/Sub Export",{"claudeCode":357},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/pubsub/plugin.json",[361],{"path":270,"priority":271},{"basePath":363,"description":364,"displayName":365,"installMethods":366,"rationale":367,"selectedPaths":368,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/rudderstack-posthog","Send event data to RudderStack","RudderStack",{"claudeCode":365},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/rudderstack-posthog/plugin.json",[369],{"path":270,"priority":271},{"basePath":371,"description":372,"displayName":373,"installMethods":374,"rationale":375,"selectedPaths":376,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/salesforce","Relay PostHog events to Salesforce","Salesforce Export Plugin",{"claudeCode":373},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/salesforce/plugin.json",[377],{"path":270,"priority":271},{"basePath":379,"description":380,"displayName":381,"installMethods":382,"rationale":383,"selectedPaths":384,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_destinations/sendgrid","Send emails and user data to Sendgrid when you identify users using PostHog.","Sendgrid",{"claudeCode":381},"plugin manifest at nodejs/src/cdp/legacy-plugins/_destinations/sendgrid/plugin.json",[385],{"path":270,"priority":271},{"basePath":387,"displayName":388,"installMethods":389,"rationale":390,"selectedPaths":391,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/Plugin-Stonly-Clean-Campaign-Name","Clean Campaign Name",{"claudeCode":388},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/Plugin-Stonly-Clean-Campaign-Name/plugin.json",[392],{"path":270,"priority":271},{"basePath":394,"description":395,"displayName":396,"installMethods":397,"rationale":398,"selectedPaths":399,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/currency-normalization-plugin","Deprecated","Currency Normalization",{"claudeCode":396},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/currency-normalization-plugin/plugin.json",[400],{"path":270,"priority":271},{"basePath":402,"description":403,"displayName":404,"installMethods":405,"rationale":406,"selectedPaths":407,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/downsampling-plugin","Reduces event volume coming into PostHog","Downsampling Plugin",{"claudeCode":404},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/downsampling-plugin/plugin.json",[408],{"path":270,"priority":271},{"basePath":410,"description":411,"displayName":412,"installMethods":413,"rationale":414,"selectedPaths":415,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/drop-events-on-property-plugin","This plugin will drop any events that have a specific key. If you supply a value, it will drop any event with the combination of they key and the value. You will not be billed for any events that this plugin drops.","Drop Events Based On Property",{"claudeCode":412},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/drop-events-on-property-plugin/plugin.json",[416],{"path":270,"priority":271},{"basePath":418,"description":419,"displayName":420,"installMethods":421,"rationale":422,"selectedPaths":423,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/first-time-event-tracker","Deprecated.","First Time Event Tracker",{"claudeCode":420},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/first-time-event-tracker/plugin.json",[424],{"path":270,"priority":271},{"basePath":426,"description":427,"displayName":428,"installMethods":429,"rationale":430,"selectedPaths":431,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/flatten-properties-plugin","Flatten event properties to easily access them in filters.","Property Flattener Plugin",{"claudeCode":428},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/flatten-properties-plugin/plugin.json",[432],{"path":270,"priority":271},{"basePath":434,"displayName":435,"installMethods":436,"rationale":437,"selectedPaths":438,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/language-url-splitter-app","Language URL stripper",{"claudeCode":435},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/language-url-splitter-app/plugin.json",[439],{"path":270,"priority":271},{"basePath":441,"description":442,"displayName":443,"installMethods":444,"rationale":445,"selectedPaths":446,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/ph-shotgun-processevent-app","A custom app to rename specific event names during the migration of Shotgun events from US to EU","ph-shotgun-processevent-app",{"claudeCode":443},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/ph-shotgun-processevent-app/plugin.json",[447],{"path":270,"priority":271},{"basePath":449,"description":450,"displayName":451,"installMethods":452,"rationale":453,"selectedPaths":454,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/plugin-advanced-geoip","Advanced GeoIP filtering app for PostHog","Advanced GeoIP",{"claudeCode":451},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/plugin-advanced-geoip/plugin.json",[455],{"path":270,"priority":271},{"basePath":457,"description":458,"displayName":459,"installMethods":460,"rationale":461,"selectedPaths":462,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/plugin-netdata-event-processing","A Posthog plugin to do some data processing on our Posthog events as they arrive.","PostHog Netdata Event Processing",{"claudeCode":459},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/plugin-netdata-event-processing/plugin.json",[463],{"path":270,"priority":271},{"basePath":465,"displayName":466,"installMethods":467,"rationale":468,"selectedPaths":469,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/plugin-stonly-UTM-Extractor","UTM Extractor",{"claudeCode":466},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/plugin-stonly-UTM-Extractor/plugin.json",[470],{"path":270,"priority":271},{"basePath":472,"description":473,"displayName":473,"installMethods":474,"rationale":475,"selectedPaths":476,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/posthog-anonymization","Anonymization and normalisation",{"claudeCode":473},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/posthog-anonymization/plugin.json",[477],{"path":270,"priority":271},{"basePath":479,"description":480,"displayName":481,"installMethods":482,"rationale":483,"selectedPaths":484,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/posthog-app-unduplicator","Prevent duplicates in your data when ingesting.","Unduplicates",{"claudeCode":481},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/posthog-app-unduplicator/plugin.json",[485],{"path":270,"priority":271},{"basePath":487,"description":488,"displayName":489,"installMethods":490,"rationale":491,"selectedPaths":492,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/posthog-app-url-parameters-to-event-properties","Converts URL query parameters to event properties","URL parameters to event properties",{"claudeCode":489},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/posthog-app-url-parameters-to-event-properties/plugin.json",[493],{"path":270,"priority":271},{"basePath":495,"description":496,"displayName":497,"installMethods":498,"rationale":499,"selectedPaths":500,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/posthog-filter-out-plugin","Filter out events where property values satisfy the given condition","Filter Out Plugin",{"claudeCode":497},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/posthog-filter-out-plugin/plugin.json",[501],{"path":270,"priority":271},{"basePath":503,"description":504,"displayName":505,"installMethods":506,"rationale":507,"selectedPaths":508,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/posthog-plugin-geoip","Enrich PostHog events and persons with IP location data","GeoIP",{"claudeCode":505},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/posthog-plugin-geoip/plugin.json",[509],{"path":270,"priority":271},{"basePath":511,"displayName":512,"installMethods":513,"rationale":514,"selectedPaths":515,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/posthog-plugin-snowplow-referer-parser","UTM Referrer",{"claudeCode":512},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/posthog-plugin-snowplow-referer-parser/plugin.json",[516],{"path":270,"priority":271},{"basePath":518,"description":519,"displayName":520,"installMethods":521,"rationale":522,"selectedPaths":523,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/posthog-route-censor-plugin","Removes segments of URLs based on route patterns.","Route Censor",{"claudeCode":520},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/posthog-route-censor-plugin/plugin.json",[524],{"path":270,"priority":271},{"basePath":526,"description":527,"displayName":528,"installMethods":529,"rationale":530,"selectedPaths":531,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/posthog-url-normalizer-plugin","A PostHog plugin to normalize the format of urls in your application allowing you to more easily compare them in insights.","URL Normalizer",{"claudeCode":528},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/posthog-url-normalizer-plugin/plugin.json",[532],{"path":270,"priority":271},{"basePath":534,"description":535,"displayName":536,"installMethods":537,"rationale":538,"selectedPaths":539,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/property-filter-plugin","This plugin will set all configured properties to null inside an ingested event.","Property Filter",{"claudeCode":536},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/property-filter-plugin/plugin.json",[540],{"path":270,"priority":271},{"basePath":542,"displayName":543,"installMethods":544,"rationale":545,"selectedPaths":546,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/semver-flattener-plugin","posthog-semver-flattener",{"claudeCode":543},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/semver-flattener-plugin/plugin.json",[547],{"path":270,"priority":271},{"basePath":549,"description":550,"displayName":551,"installMethods":552,"rationale":553,"selectedPaths":554,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/taxonomy-plugin","Standardize your event names into a single pattern.","Taxonomy Plugin",{"claudeCode":551},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/taxonomy-plugin/plugin.json",[555],{"path":270,"priority":271},{"basePath":557,"description":558,"displayName":559,"installMethods":560,"rationale":561,"selectedPaths":562,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/timestamp-parser-plugin","Parse your event timestamps into useful date properties.","Timestamp Parser",{"claudeCode":559},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/timestamp-parser-plugin/plugin.json",[563],{"path":270,"priority":271},{"basePath":565,"displayName":566,"installMethods":567,"rationale":568,"selectedPaths":569,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/url-parser","URL Params Parser (Beta)",{"claudeCode":566},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/url-parser/plugin.json",[570],{"path":270,"priority":271},{"basePath":572,"description":573,"displayName":574,"installMethods":575,"rationale":576,"selectedPaths":577,"source":272,"sourceLanguage":18,"type":273},"nodejs/src/cdp/legacy-plugins/_transformations/user-agent-plugin","Enhances events with user agent details","User Agent Populator",{"claudeCode":574},"plugin manifest at nodejs/src/cdp/legacy-plugins/_transformations/user-agent-plugin/plugin.json",[578],{"path":270,"priority":271},{"basePath":580,"description":581,"displayName":582,"installMethods":583,"rationale":584,"selectedPaths":585,"source":272,"sourceLanguage":18,"type":247},".agents/skills/adding-personhog-rpc","Guide for adding a new RPC to personhog-replica and personhog-router. Covers eligibility checks, proto definition, code generation for Python and Node.js clients, Rust implementation (storage trait, postgres queries, service handler, router wiring), and index compatibility validation. Use when adding a new gRPC endpoint to personhog, migrating a Django ORM query to personhog, or extending the personhog service API.\n","adding-personhog-rpc",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/adding-personhog-rpc/SKILL.md",[586,588,591],{"path":587,"priority":271},"SKILL.md",{"path":589,"priority":590},"references/database-indexes.md","medium",{"path":592,"priority":590},"references/proto-conventions.md",{"basePath":594,"description":595,"displayName":596,"installMethods":597,"rationale":598,"selectedPaths":599,"source":272,"sourceLanguage":18,"type":247},".agents/skills/adopting-generated-api-types","Use when migrating frontend code from manual API client calls (`api.get`, `api.create`, `api.surveys.get`, `api.dashboards.list`, `new ApiRequest()`) and handwritten TypeScript interfaces to generated API functions and types. Triggers on files importing from `lib/api`, files with `api.get\u003C`, `api.create\u003C`, `api.\u003Centity>.\u003Cmethod>`, manual interface definitions that duplicate backend serializers, or any frontend file that constructs API URLs by hand. Covers the full replacement workflow — finding the generated equivalent, swapping imports, adapting call sites, and removing dead manual types.","adopting-generated-api-types",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/adopting-generated-api-types/SKILL.md",[600,601,603],{"path":587,"priority":271},{"path":602,"priority":590},"references/migration-patterns.md",{"path":604,"priority":590},"references/type-compatibility.md",{"basePath":606,"description":607,"displayName":608,"installMethods":609,"rationale":610,"selectedPaths":611,"source":272,"sourceLanguage":18,"type":247},".agents/skills/clickhouse-migrations","ClickHouse migration patterns and rules. Use when creating or modifying ClickHouse migrations.","clickhouse-migrations",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/clickhouse-migrations/SKILL.md",[612],{"path":587,"priority":271},{"basePath":614,"description":615,"displayName":616,"installMethods":617,"rationale":618,"selectedPaths":619,"source":272,"sourceLanguage":18,"type":247},".agents/skills/debugging-ci-failures","Debugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches. Use when the user asks why CI is red, mentions a failing check, GitHub Actions run, Depot runner, workflow, job, shard, flaky test, lint failure, typecheck failure, snapshot diff, migration check, generated types drift, or skills build failure. Guides read-only inspection, failure classification, smallest local reproduction with hogli, and safe reporting without rerunning CI or posting to GitHub.\n","debugging-ci-failures",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/debugging-ci-failures/SKILL.md",[620],{"path":587,"priority":271},{"basePath":622,"description":623,"displayName":624,"installMethods":625,"rationale":626,"selectedPaths":627,"source":272,"sourceLanguage":18,"type":247},".agents/skills/django-migrations","Django migration patterns and safety workflow for PostHog. Use when creating, adjusting, or reviewing Django/Postgres migrations, including non-blocking index/constraint changes, multi-phase schema changes, data backfills, migration conflict rebasing, and product model moves that require SeparateDatabaseAndState.","django-migrations",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/django-migrations/SKILL.md",[628],{"path":587,"priority":271},{"basePath":630,"description":631,"displayName":632,"installMethods":633,"rationale":634,"selectedPaths":635,"source":272,"sourceLanguage":18,"type":247},".agents/skills/hogli","PostHog developer CLI and repo tooling reference. Use when the user mentions hogli, asks about repo CLI tools, bin scripts, Makefiles, how to run/build/test/lint, or any dev environment commands.\n","hogli",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/hogli/SKILL.md",[636],{"path":587,"priority":271},{"basePath":638,"description":639,"displayName":640,"installMethods":641,"rationale":642,"selectedPaths":643,"source":272,"sourceLanguage":18,"type":247},".agents/skills/implementing-agent-modes","Guidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what conditions. Achieve better results using your plan mode.","implementing-agent-modes",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/implementing-agent-modes/SKILL.md",[644],{"path":587,"priority":271},{"basePath":646,"description":647,"displayName":648,"installMethods":649,"rationale":650,"selectedPaths":651,"source":272,"sourceLanguage":18,"type":247},".agents/skills/implementing-mcp-tools","Guide for exposing PostHog product endpoints as MCP tools. Use when creating new or updating API endpoints, adding MCP tool definitions, scaffolding YAML configs, or writing serializers with good descriptions. Covers the full pipeline from Django serializer to generated TypeScript tool handler.","implementing-mcp-tools",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/implementing-mcp-tools/SKILL.md",[652],{"path":587,"priority":271},{"basePath":654,"description":655,"displayName":656,"installMethods":657,"rationale":658,"selectedPaths":659,"source":272,"sourceLanguage":18,"type":247},".agents/skills/implementing-mcp-ui-apps","Guide for adding MCP UI apps — interactive visualizations that render tool results in MCP clients like Claude Desktop. Use when adding a new detail or list view for an MCP tool, creating view components in products/*/mcp/apps/, or linking tools to UI apps via YAML.","implementing-mcp-ui-apps",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/implementing-mcp-ui-apps/SKILL.md",[660],{"path":587,"priority":271},{"basePath":662,"description":663,"displayName":664,"installMethods":665,"rationale":666,"selectedPaths":667,"source":272,"sourceLanguage":18,"type":247},".agents/skills/implementing-warehouse-sources","Implement and extend PostHog Data warehouse import sources. Use when adding a new source under posthog/temporal/data_imports/sources, adding datasets/endpoints to an existing source, or adding incremental sync, resumable imports, webhook ingestion, pagination, credentials validation, and source tests.","implementing-warehouse-sources",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/implementing-warehouse-sources/SKILL.md",[668],{"path":587,"priority":271},{"basePath":670,"description":671,"displayName":672,"installMethods":673,"rationale":674,"selectedPaths":675,"source":272,"sourceLanguage":18,"type":247},".agents/skills/improving-drf-endpoints","Use when editing, reviewing, or auditing DRF viewsets and serializers in PostHog. Triggers on files in posthog/api/, products/*/backend/api/, products/*/backend/presentation/, or any file importing rest_framework. Covers field typing, schema annotations, enum collision fixes, and OpenAPI spec quality — everything that flows downstream into generated TypeScript types and MCP tools.","improving-drf-endpoints",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/improving-drf-endpoints/SKILL.md",[676,677,679,681,683],{"path":587,"priority":271},{"path":678,"priority":590},"references/common-anti-patterns.md",{"path":680,"priority":590},"references/quick-reference-table.md",{"path":682,"priority":590},"references/serializer-fields.md",{"path":684,"priority":590},"references/viewset-annotations.md",{"basePath":686,"description":687,"displayName":688,"installMethods":689,"rationale":690,"selectedPaths":691,"source":272,"sourceLanguage":18,"type":247},".agents/skills/ingestion-pipeline-doctor-nodejs","Ingestion pipeline architecture overview and convention reference. Use when you need a quick orientation to the pipeline framework or want to know which doctor agent to use for a specific concern.\n","ingestion-pipeline-doctor-nodejs",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/ingestion-pipeline-doctor-nodejs/SKILL.md",[692],{"path":587,"priority":271},{"basePath":694,"description":695,"displayName":696,"installMethods":697,"rationale":698,"selectedPaths":699,"source":272,"sourceLanguage":18,"type":247},".agents/skills/isolating-product-facade-contracts","Plan and execute incremental product isolation migrations to a facade plus contract layer in PostHog, following the Visual review architecture. Use when a product still exposes internals (models/logic/views) across boundaries and needs a safe, multi-PR migration toward contracts.py + facade/api.py + presentation separation.","isolating-product-facade-contracts",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/isolating-product-facade-contracts/SKILL.md",[700,701],{"path":587,"priority":271},{"path":702,"priority":590},"references/phased-migration-plan.md",{"basePath":704,"description":705,"displayName":706,"installMethods":707,"rationale":708,"selectedPaths":709,"source":272,"sourceLanguage":18,"type":247},".agents/skills/making-scenes-tab-aware","Guides converting PostHog frontend scenes to be tab aware for internal scene tabs. Use when adding or refactoring a `SceneExport` scene, fixing state leaking between internal tabs, preserving scene state across tab switches, or moving scene-level URL state out of child logics. Triggers on files with `SceneExport`, `tabId`, `tabAwareScene`, `urlToAction`, `actionToUrl`, or `useAttachedLogic`.","making-scenes-tab-aware",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/making-scenes-tab-aware/SKILL.md",[710,711,713,715],{"path":587,"priority":271},{"path":712,"priority":590},"references/audit-commands.md",{"path":714,"priority":590},"references/migration-checklist.md",{"path":716,"priority":590},"references/repo-patterns.md",{"basePath":718,"description":719,"displayName":720,"installMethods":721,"rationale":722,"selectedPaths":723,"source":272,"sourceLanguage":18,"type":247},".agents/skills/modifying-taxonomic-filter","Guides safe modification of the TaxonomicFilter — PostHog's multi-tab picker for events, actions, properties, cohorts, and more. Front-loads the empirical product reality (what users actually pick and search for) so changes can be judged against real behavior, not architectural taste. Use when adding features, fixing bugs, or refactoring TaxonomicFilter.","modifying-taxonomic-filter",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/modifying-taxonomic-filter/SKILL.md",[724,725,727,729,731,733],{"path":587,"priority":271},{"path":726,"priority":590},"references/architecture.md",{"path":728,"priority":590},"references/call-sites-and-blast-radius.md",{"path":730,"priority":590},"references/common-pitfalls.md",{"path":732,"priority":590},"references/refreshing-product-reality.md",{"path":734,"priority":590},"references/testing-patterns.md",{"basePath":736,"description":737,"displayName":738,"installMethods":739,"rationale":740,"selectedPaths":741,"source":272,"sourceLanguage":18,"type":247},".agents/skills/monitoring-capture-service","Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production. Use when investigating latency, event loss, Kafka backpressure, Redis issues, rate limiting, Envoy proxy issues, or any capture health question. Covers prod-us and prod-eu environments.\n","monitoring-capture-service",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/monitoring-capture-service/SKILL.md",[742,743],{"path":587,"priority":271},{"path":744,"priority":590},"references/investigation-playbooks.md",{"basePath":746,"description":747,"displayName":748,"installMethods":749,"rationale":750,"selectedPaths":751,"source":272,"sourceLanguage":18,"type":247},".agents/skills/monitoring-ingestion-pipeline","Guide for using the Grafana MCP to monitor and diagnose the Node.js ingestion pipeline workers in production. Use when investigating event lag, drops, pipeline errors, person/group processing, Kafka consumer health, Redis, Postgres, ClickHouse downstream health, or any ingestion worker question. Covers prod-us and prod-eu environments.\n","monitoring-ingestion-pipeline",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/monitoring-ingestion-pipeline/SKILL.md",[752,753],{"path":587,"priority":271},{"path":744,"priority":590},{"basePath":755,"description":756,"displayName":757,"installMethods":758,"rationale":759,"selectedPaths":760,"source":272,"sourceLanguage":18,"type":247},".agents/skills/playwright-test","Write a playwright test, make sure it runs, and is not flaky.","playwright-test",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/playwright-test/SKILL.md",[761],{"path":587,"priority":271},{"basePath":763,"description":764,"displayName":765,"installMethods":766,"rationale":767,"selectedPaths":768,"source":272,"sourceLanguage":18,"type":247},".agents/skills/qa-team","Multi-agent QA review team for code changes. This skill should be used when the user asks to \"review my code\", \"run QA\", \"qa-team\", \"review this branch\", \"code review\", \"check my changes\", or wants a comprehensive multi-perspective code review of the current branch's changes. Spawns parallel specialist agents (security, database, reliability, compatibility, data integrity, performance, frontend, copy) that independently review the diff and produce a converged report. Also includes two generalist reviewers for convergence validation.\n","qa-team",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/qa-team/SKILL.md",[769,770,772],{"path":587,"priority":271},{"path":771,"priority":590},"references/incident-patterns.md",{"path":773,"priority":590},"references/personas.md",{"basePath":775,"description":776,"displayName":777,"installMethods":778,"rationale":779,"selectedPaths":780,"source":272,"sourceLanguage":18,"type":247},".agents/skills/query-clickhouse-via-metabase","Run ClickHouse `system.query_log` analysis via the internal Metabase API. Use when investigating slow queries, materialization candidates, per-team query performance, ClickHouse cost or memory issues, or any system.query_log question. Covers prod-us and prod-eu, SSO-gated cookie auth via `hogli`, and ready-to-run query patterns.\n","query-clickhouse-via-metabase",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/query-clickhouse-via-metabase/SKILL.md",[781],{"path":587,"priority":271},{"basePath":783,"description":784,"displayName":785,"installMethods":786,"rationale":787,"selectedPaths":788,"source":272,"sourceLanguage":18,"type":247},".agents/skills/react-doctor","Diagnose and fix React codebase health issues. Use when reviewing React code, fixing performance problems, auditing security, or improving code quality.","react-doctor",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/react-doctor/SKILL.md",[789],{"path":587,"priority":271},{"basePath":791,"description":792,"displayName":793,"installMethods":794,"rationale":795,"selectedPaths":796,"source":272,"sourceLanguage":18,"type":247},".agents/skills/scene-menu-bar","Conventions for adding or editing the SceneMenuBar above a scene's \u003CSceneTitleSection>. Use when adding new menu items, moving items between menus, gating behind feature flags, building a new scene's menubar, or wiring rich inputs (tags, combobox) into the bar.","scene-menu-bar",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/scene-menu-bar/SKILL.md",[797],{"path":587,"priority":271},{"basePath":799,"description":800,"displayName":801,"installMethods":802,"rationale":803,"selectedPaths":804,"source":272,"sourceLanguage":18,"type":247},".agents/skills/sending-notifications","How to send real-time in-app notifications from PostHog backend code. Use when integrating notifications into a new feature, wiring up a notification source (alerts, comments, approvals, pipelines, issues), or choosing the right target type and priority for a notification.","sending-notifications",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/sending-notifications/SKILL.md",[805],{"path":587,"priority":271},{"basePath":807,"description":808,"displayName":809,"installMethods":810,"rationale":811,"selectedPaths":812,"source":272,"sourceLanguage":18,"type":247},".agents/skills/setup-web-tests","Set up Python test environment in Claude Code for web where flox is unavailable. Use when you need to run backend tests and `uv sync` fails due to Python version mismatch.","setup-web-tests",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/setup-web-tests/SKILL.md",[813],{"path":587,"priority":271},{"basePath":815,"description":816,"displayName":817,"installMethods":818,"rationale":819,"selectedPaths":820,"source":272,"sourceLanguage":18,"type":247},".agents/skills/survey-sdk-audit","Audit PostHog survey SDK features and version requirements","survey-sdk-audit",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/survey-sdk-audit/SKILL.md",[821],{"path":587,"priority":271},{"basePath":823,"description":824,"displayName":825,"installMethods":826,"rationale":827,"selectedPaths":828,"source":272,"sourceLanguage":18,"type":247},".agents/skills/using-kea-disposables","Use when adding timers (`setInterval`, `setTimeout`), event listeners (`window.addEventListener`, `document.addEventListener`, `MediaQueryList.addEventListener`), or any other resource that needs cleanup inside a kea logic. Every logic has `cache.disposables.add(setup, key?, options?)` and `cache.disposables.dispose(key)` available via the globally registered `disposablesPlugin` (`frontend/src/kea-disposables.ts`). Replaces the bare `cache.foo = setInterval(...)` + `beforeUnmount: clearInterval(cache.foo)` pattern and auto-pauses background work when the tab is hidden.","using-kea-disposables",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/using-kea-disposables/SKILL.md",[829],{"path":587,"priority":271},{"basePath":831,"description":832,"displayName":833,"installMethods":834,"rationale":835,"selectedPaths":836,"source":272,"sourceLanguage":18,"type":247},".agents/skills/writing-skills","Guide for writing PostHog agent skills — job-to-be-done templates that teach agents how to use MCP tools to achieve a goal. Use when adding new product functionality that agents should know how to work with, creating a new skill, or updating existing skills in products/*/skills/.","writing-skills",{"claudeCode":12},"SKILL.md frontmatter at .agents/skills/writing-skills/SKILL.md",[837],{"path":587,"priority":271},{"basePath":839,"description":840,"displayName":841,"installMethods":842,"rationale":843,"selectedPaths":844,"source":272,"sourceLanguage":18,"type":247},"products/data_warehouse/skills/auditing-warehouse-data-health","Audit the health of a PostHog project's data warehouse — find every broken or degraded pipeline item across sources, sync schemas, materialized views, batch exports, and transformations. Use when the user asks \"what's broken in my warehouse?\", \"give me a health check\", \"audit my data pipeline\", \"why are some dashboards stale?\", or wants a one-shot triage summary before deciding where to spend time. Produces a prioritized report of issues grouped by severity and type, with recommended next steps.\n","auditing-warehouse-data-health",{"claudeCode":12},"SKILL.md frontmatter at products/data_warehouse/skills/auditing-warehouse-data-health/SKILL.md",[845],{"path":587,"priority":271},{"basePath":847,"description":848,"displayName":849,"installMethods":850,"rationale":851,"selectedPaths":852,"source":272,"sourceLanguage":18,"type":247},"products/data_warehouse/skills/diagnosing-failed-warehouse-syncs","Diagnose why a data warehouse sync is failing and recommend the right recovery action. Use when the user asks \"why isn't my Stripe/Postgres/Hubspot sync working?\", \"this table has been stuck for hours\", \"the data in the warehouse looks wrong\", or wants to troubleshoot a specific source or schema. Covers source-level vs schema-level failures, stuck Running states, credential and schema-drift errors, incremental-field misconfig, CDC prerequisite failures, and the cancel / reload / resync / delete-data recovery actions.\n","diagnosing-failed-warehouse-syncs",{"claudeCode":12},"SKILL.md frontmatter at products/data_warehouse/skills/diagnosing-failed-warehouse-syncs/SKILL.md",[853],{"path":587,"priority":271},{"basePath":855,"description":856,"displayName":857,"installMethods":858,"rationale":859,"selectedPaths":860,"source":272,"sourceLanguage":18,"type":247},"products/data_warehouse/skills/setting-up-a-data-warehouse-source","Guide the user through connecting a new data warehouse source — Postgres, MySQL, Stripe, Hubspot, MongoDB, Salesforce, BigQuery, Snowflake, and so on. Use when the user wants to \"connect Stripe\", \"import data from Postgres\", \"add a new data source\", \"sync my warehouse tables\", or wants to pick sync methods for each table. Walks through source-type discovery, credential validation, table discovery, per-table sync_type selection, and the final create call. Also covers picking a good prefix and what to do right after creation.\n","setting-up-a-data-warehouse-source",{"claudeCode":12},"SKILL.md frontmatter at products/data_warehouse/skills/setting-up-a-data-warehouse-source/SKILL.md",[861,862],{"path":587,"priority":271},{"path":863,"priority":590},"references/sync-types.md",{"basePath":865,"description":866,"displayName":867,"installMethods":868,"rationale":869,"selectedPaths":870,"source":272,"sourceLanguage":18,"type":247},"products/data_warehouse/skills/suggesting-data-imports","Use when the user asks about revenue, payments, subscriptions, billing, CRM deals, support tickets, production database tables, or other data that PostHog does not collect natively. Also use when a query fails because a table does not exist or returns no results for expected external data. The data warehouse can import from SaaS tools (Stripe, Hubspot, etc.), production databases (Postgres, MySQL, BigQuery, Snowflake), and other arbitrary data sources. Covers checking existing sources, identifying the right source type, and guiding the setup.","suggesting-data-imports",{"claudeCode":12},"SKILL.md frontmatter at products/data_warehouse/skills/suggesting-data-imports/SKILL.md",[871],{"path":587,"priority":271},{"basePath":873,"description":874,"displayName":875,"installMethods":876,"rationale":877,"selectedPaths":878,"source":272,"sourceLanguage":18,"type":247},"products/data_warehouse/skills/tuning-incremental-sync-config","Change the sync configuration of an existing data warehouse schema — switch sync_type, pick a different incremental_field, set primary_key_columns, choose cdc_table_mode, or change sync_frequency. Use when the user asks \"switch my orders table from full refresh to incremental\", \"this table is syncing too slowly / too frequently\", \"I need to pick a different incremental column\", \"set up CDC for this Postgres table\", or when diagnosis of a failing sync pointed to an incremental-field or PK misconfiguration.\n","tuning-incremental-sync-config",{"claudeCode":12},"SKILL.md frontmatter at products/data_warehouse/skills/tuning-incremental-sync-config/SKILL.md",[879],{"path":587,"priority":271},{"basePath":881,"description":882,"displayName":883,"installMethods":884,"rationale":885,"selectedPaths":886,"source":272,"sourceLanguage":18,"type":247},"products/experiments/skills/analyzing-experiment-session-replays","Analyze session replay patterns across experiment variants to understand user behavior differences. Use when the user wants to see how users interact with different experiment variants, identify usability issues, compare behavior patterns between control and test groups, or get qualitative insights to complement quantitative experiment results.","analyzing-experiment-session-replays",{"claudeCode":12},"SKILL.md frontmatter at products/experiments/skills/analyzing-experiment-session-replays/SKILL.md",[887],{"path":587,"priority":271},{"basePath":889,"description":890,"displayName":891,"installMethods":892,"rationale":893,"selectedPaths":894,"source":272,"sourceLanguage":18,"type":247},"products/experiments/skills/configuring-experiment-analytics","Configures the analytics side of a PostHog experiment — exposure criteria (default `$feature_flag_called` vs custom exposure events), primary and secondary metrics, the supported metric types (count, sum, ratio with `math` and `math_property`, retention with `retention_window_start` and `start_handling`), multivariate user handling (\"Exclude\" vs \"First seen variant\"), and how to read results once the experiment is live. Use when the user adds or edits a primary or secondary metric (e.g. \"add a secondary metric tracking 'downloaded_file' per user\"), sets up a ratio metric (e.g. \"revenue from purchase_completed / pageviews\"), sets up a retention metric (e.g. \"$pageview → uploaded_file, 7-day window\"), configures custom exposure (e.g. \"only count users who hit /checkout\"), changes multivariate handling, or asks \"who is in the analysis?\", \"how do I measure impact?\", \"is this winning?\", \"what's the confidence level?\", or \"should I ship?\".","configuring-experiment-analytics",{"claudeCode":12},"SKILL.md frontmatter at products/experiments/skills/configuring-experiment-analytics/SKILL.md",[895,896,898],{"path":587,"priority":271},{"path":897,"priority":590},"references/interpreting-results.md",{"path":899,"priority":590},"references/metric-configuration.md",{"basePath":901,"description":902,"displayName":903,"installMethods":904,"rationale":905,"selectedPaths":906,"source":272,"sourceLanguage":18,"type":247},"products/experiments/skills/configuring-experiment-rollout","Configures the rollout shape of a PostHog experiment — the variant split (50/50, 80/20, A/B/C ratios), the overall rollout percentage that gates how many users enter the experiment, and the disambiguation when a percentage like \"roll out to 25%\" could mean either. Use when the user mentions a rollout percentage, variant split, or traffic distribution; gives a ratio like 60/40, 70/30, or 80/20; asks \"who sees the test variant?\"; wants to increase, decrease, or change the rollout or split on a draft or running experiment; weighs equal vs uneven splits; or proposes a mid-experiment split change (often an anti-pattern that needs reset or end-and-restart).","configuring-experiment-rollout",{"claudeCode":12},"SKILL.md frontmatter at products/experiments/skills/configuring-experiment-rollout/SKILL.md",[907,908],{"path":587,"priority":271},{"path":909,"priority":590},"references/changing-distribution-after-launch.md",{"basePath":245,"description":10,"displayName":13,"installMethods":911,"rationale":912,"selectedPaths":913,"source":272,"sourceLanguage":18,"type":247},{"claudeCode":12},"SKILL.md frontmatter at products/experiments/skills/creating-experiments/SKILL.md",[914],{"path":587,"priority":271},{"basePath":916,"description":917,"displayName":918,"installMethods":919,"rationale":920,"selectedPaths":921,"source":272,"sourceLanguage":18,"type":247},"products/experiments/skills/finding-experiments","Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with disambiguation when multiple experiments match. Use when the user names or quotes an experiment (\"split test demo\", \"the File engagement boost experiment\", \"onboarding retention test\", \"landing page hero experiment\", \"pricing experiment\"), describes it loosely (\"the signup experiment\", \"my pricing test\", \"the one with the new checkout\"), uses a relative reference (\"latest\", \"most recent\", \"the one I created yesterday\"), filters by status (running, draft, stopped, archived), or otherwise refers to an experiment by anything other than its concrete ID.","finding-experiments",{"claudeCode":12},"SKILL.md frontmatter at products/experiments/skills/finding-experiments/SKILL.md",[922],{"path":587,"priority":271},{"basePath":924,"description":925,"displayName":926,"installMethods":927,"rationale":928,"selectedPaths":929,"source":272,"sourceLanguage":18,"type":247},"products/experiments/skills/managing-experiment-lifecycle","Guides experiment state transitions: launching, pausing, resuming, ending, shipping variants, archiving, resetting, and duplicating. Covers preconditions, implications for variant assignment and analysis, and the decision framework for when to use each action.\nTRIGGER when: user asks to launch, pause, resume, end, ship, archive, reset, or duplicate an experiment.\nDO NOT TRIGGER when: user is creating an experiment (use creating-experiments), configuring rollout (use configuring-experiment-rollout), or setting up metrics (use configuring-experiment-analytics).","managing-experiment-lifecycle",{"claudeCode":12},"SKILL.md frontmatter at products/experiments/skills/managing-experiment-lifecycle/SKILL.md",[930],{"path":587,"priority":271},{"basePath":932,"description":933,"displayName":934,"installMethods":935,"rationale":936,"selectedPaths":937,"source":272,"sourceLanguage":18,"type":247},"products/feature_flags/skills/cleaning-up-stale-feature-flags","Identify and clean up stale feature flags in a PostHog project. Use when the user wants to find unused, fully rolled out, or abandoned feature flags, review them for safety, and then disable or delete them. Covers staleness detection, dependency checking, and safe removal workflows.","cleaning-up-stale-feature-flags",{"claudeCode":12},"SKILL.md frontmatter at products/feature_flags/skills/cleaning-up-stale-feature-flags/SKILL.md",[938],{"path":587,"priority":271},{"basePath":940,"description":941,"displayName":942,"installMethods":943,"rationale":944,"selectedPaths":945,"source":272,"sourceLanguage":18,"type":247},"products/feature_flags/skills/copying-flags-across-projects","Copy a feature flag from one PostHog project to one or more target projects in the same organization. Use when the user wants to duplicate a flag, promote a flag from staging to production, sync flags across projects, or replicate a flag configuration in a different workspace. Covers cohort remapping, scheduled-change handling, encrypted payloads, and the safe defaults (disabled in target, no scheduled changes).","copying-flags-across-projects",{"claudeCode":12},"SKILL.md frontmatter at products/feature_flags/skills/copying-flags-across-projects/SKILL.md",[946],{"path":587,"priority":271},{"basePath":948,"description":949,"displayName":950,"installMethods":951,"rationale":952,"selectedPaths":953,"source":272,"sourceLanguage":18,"type":247},"products/growth/skills/diagnosing-sdk-health","Diagnoses the health of a project's PostHog SDK integrations — which SDKs are up to date, which are outdated, and what to do about it. Use when a user asks about PostHog SDK versions, outdated SDKs, upgrade recommendations, \"SDK health\", \"SDK doctor\", or when events or features seem off and it might be due to using an old SDK.\n","diagnosing-sdk-health",{"claudeCode":12},"SKILL.md frontmatter at products/growth/skills/diagnosing-sdk-health/SKILL.md",[954],{"path":587,"priority":271},{"basePath":956,"description":957,"displayName":958,"installMethods":959,"rationale":960,"selectedPaths":961,"source":272,"sourceLanguage":18,"type":247},"products/llm_analytics/skills/exploring-llm-clusters","Investigate LLM analytics clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into individual traces within clusters.","exploring-llm-clusters",{"claudeCode":12},"SKILL.md frontmatter at products/llm_analytics/skills/exploring-llm-clusters/SKILL.md",[962,963],{"path":587,"priority":271},{"path":964,"priority":965},"scripts/print_clusters.py","low",{"basePath":967,"description":968,"displayName":969,"installMethods":970,"rationale":971,"selectedPaths":972,"source":272,"sourceLanguage":18,"type":247},"products/llm_analytics/skills/exploring-llm-costs","Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks \"how much are we spending on LLMs?\", \"which model / user / feature is most expensive?\", \"why did cost spike?\", wants to build a cost dashboard or alert, or pastes a trace URL and asks about its cost.\n","exploring-llm-costs",{"claudeCode":12},"SKILL.md frontmatter at products/llm_analytics/skills/exploring-llm-costs/SKILL.md",[973,974,976,978,980,982,984],{"path":587,"priority":271},{"path":975,"priority":590},"references/breakdown-patterns.md",{"path":977,"priority":590},"references/cache-accounting.md",{"path":979,"priority":590},"references/cost-properties.md",{"path":981,"priority":590},"references/cost-sources.md",{"path":983,"priority":590},"references/materializing.md",{"path":985,"priority":590},"references/regression-debugging.md",{"basePath":987,"description":988,"displayName":989,"installMethods":990,"rationale":991,"selectedPaths":992,"source":272,"sourceLanguage":18,"type":247},"products/llm_analytics/skills/exploring-llm-evaluations","Investigate LLM analytics evaluations of both types — `hog` (deterministic code-based) and `llm_judge` (LLM-prompt-based). Find existing evaluations, inspect their configuration, run them against specific generations, query individual pass/fail results, and generate AI-powered summaries of patterns across many runs. Use when the user asks to debug why an evaluation is failing, surface common failure modes, compare results across filters, dry-run a Hog evaluator, prototype a new LLM-judge prompt, or manage the evaluation lifecycle (create, update, enable/disable, delete).\n","exploring-llm-evaluations",{"claudeCode":12},"SKILL.md frontmatter at products/llm_analytics/skills/exploring-llm-evaluations/SKILL.md",[993],{"path":587,"priority":271},{"basePath":995,"description":996,"displayName":997,"installMethods":998,"rationale":999,"selectedPaths":1000,"source":272,"sourceLanguage":18,"type":247},"products/llm_analytics/skills/exploring-llm-traces","ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /llm-analytics/traces/\u003Cid> or /llm-analytics/sessions/\u003Cid>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs.\n","exploring-llm-traces",{"claudeCode":12},"SKILL.md frontmatter at products/llm_analytics/skills/exploring-llm-traces/SKILL.md",[1001,1002,1004,1006,1008,1010,1012,1014,1016,1018],{"path":587,"priority":271},{"path":1003,"priority":590},"references/events-and-properties.md",{"path":1005,"priority":590},"references/example-llm-trace.md.j2",{"path":1007,"priority":590},"references/example-llm-traces-list.md",{"path":1009,"priority":965},"scripts/extract_conversation.py",{"path":1011,"priority":965},"scripts/extract_span.py",{"path":1013,"priority":965},"scripts/print_summary.py",{"path":1015,"priority":965},"scripts/print_timeline.py",{"path":1017,"priority":965},"scripts/search_traces.py",{"path":1019,"priority":965},"scripts/show_structure.py",{"basePath":1021,"description":1022,"displayName":1023,"installMethods":1024,"rationale":1025,"selectedPaths":1026,"source":272,"sourceLanguage":18,"type":247},"products/llm_analytics/skills/feature-usage-feed","Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use when someone wants to understand how users are actually using a specific AI/LLM-powered feature in production — what they're investigating, what questions they're trying to answer, and what patterns surface — without manually reading hundreds of traces. Assumes the feature emits `$ai_generation` and `$ai_evaluation` events with `$session_id` linkage to the trigger user's recording (the standard setup post the session-summary linkage PRs).\n","feature-usage-feed",{"claudeCode":12},"SKILL.md frontmatter at products/llm_analytics/skills/feature-usage-feed/SKILL.md",[1027],{"path":587,"priority":271},{"basePath":1029,"description":1030,"displayName":1031,"installMethods":1032,"rationale":1033,"selectedPaths":1034,"source":272,"sourceLanguage":18,"type":247},"products/llm_analytics/skills/skills-store","Discover and use shared team skills stored in PostHog. Use when the user asks to list, browse, load, or manage \"shared skills\", \"team skills\", or references the \"skills store\" / \"skill store\".","skills-store",{"claudeCode":12},"SKILL.md frontmatter at products/llm_analytics/skills/skills-store/SKILL.md",[1035],{"path":587,"priority":271},{"basePath":1037,"description":1038,"displayName":1039,"installMethods":1040,"rationale":1041,"selectedPaths":1042,"source":272,"sourceLanguage":18,"type":247},"products/llm_analytics/skills/working-with-skills","Best practices for agents managing PostHog skills via the MCP `llma-skill-*` tools — how to discover, read, create, update, and refactor skills efficiently, especially large skills with many bundled files. Use whenever you are about to call any `llma-skill-*` tool, asked to author or edit a shared skill, or troubleshoot why a skill write was rejected. Pairs with `skills-store` (which covers the raw tool surface) by adding the decision-tree, efficiency, and pitfall guidance.","working-with-skills",{"claudeCode":12},"SKILL.md frontmatter at products/llm_analytics/skills/working-with-skills/SKILL.md",[1043],{"path":587,"priority":271},{"basePath":1045,"description":1046,"displayName":1047,"installMethods":1048,"rationale":1049,"selectedPaths":1050,"source":272,"sourceLanguage":18,"type":247},"products/logs/skills/authoring-log-alerts","Author useful, low-noise log alerts on services in a PostHog project. Use when the user asks to set up alerts for their logs, suggest alerts they should add, or evaluate whether a service is worth monitoring. Covers service triage, baseline characterisation, threshold drafting, back-testing via simulate, and shipping with a notification destination.\n","authoring-log-alerts",{"claudeCode":12},"SKILL.md frontmatter at products/logs/skills/authoring-log-alerts/SKILL.md",[1051,1052,1054,1056],{"path":587,"priority":271},{"path":1053,"priority":590},"references/threshold-defaults.md",{"path":1055,"priority":590},"references/volume-floor-alerts.md",{"path":1057,"priority":965},"scripts/baseline_stats.py",{"basePath":1059,"description":1060,"displayName":1061,"installMethods":1062,"rationale":1063,"selectedPaths":1064,"source":272,"sourceLanguage":18,"type":247},"products/posthog_ai/skills/auditing-experiments-flags","Audit PostHog experiments and feature flags for configuration issues, staleness, and best-practice violations. Read when the user asks to audit, health-check, or review experiments or feature flags, check flag hygiene, or verify experiment setup.","auditing-experiments-flags",{"claudeCode":12},"SKILL.md frontmatter at products/posthog_ai/skills/auditing-experiments-flags/SKILL.md",[1065,1066,1068,1070,1072,1074],{"path":587,"priority":271},{"path":1067,"priority":590},"references/experiment-checks.md",{"path":1069,"priority":590},"references/finding-taxonomy.md",{"path":1071,"priority":590},"references/flag-checks.md.j2",{"path":1073,"priority":590},"references/remediation-actions.md",{"path":1075,"priority":590},"references/synthesis-patterns.md",{"basePath":1077,"description":1078,"displayName":1079,"installMethods":1080,"rationale":1081,"selectedPaths":1082,"source":272,"sourceLanguage":18,"type":247},"products/posthog_ai/skills/managing-subscriptions","Manage PostHog subscriptions — scheduled email, Slack, or webhook deliveries of insight or dashboard snapshots. Use when the user wants to subscribe to an insight or dashboard, check existing subscriptions, change delivery frequency, add or remove recipients, or stop receiving updates.","managing-subscriptions",{"claudeCode":12},"SKILL.md frontmatter at products/posthog_ai/skills/managing-subscriptions/SKILL.md",[1083],{"path":587,"priority":271},{"basePath":1085,"description":1086,"displayName":1087,"installMethods":1088,"rationale":1089,"selectedPaths":1090,"source":272,"sourceLanguage":18,"type":247},"products/posthog_ai/skills/querying-posthog-data","Required reading before writing any HogQL/SQL or calling execute-sql against PostHog. Use whenever the user wants to search, find, or do complex aggregations PostHog entities (insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, data warehouse, persons, etc.) and query analytics data (trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, LLM traces). Covers HogQL syntax differences from ClickHouse SQL, system table schemas (system.*), available functions, query examples, and the schema-discovery workflow.","querying-posthog-data",{"claudeCode":12},"SKILL.md frontmatter at products/posthog_ai/skills/querying-posthog-data/SKILL.md",[1091,1092,1094,1096,1098,1100,1102,1104,1105,1106,1108,1110,1112,1114,1116,1118,1120,1122,1124,1126,1128,1130,1132,1134,1136,1138,1140,1142,1144,1146,1148,1150,1152,1154,1156,1158,1160,1162,1164,1166,1168,1170,1172,1174,1176,1178,1180,1182,1184,1186,1188,1190],{"path":587,"priority":271},{"path":1093,"priority":590},"references/available-functions.md.j2",{"path":1095,"priority":590},"references/example-error-tracking.md.j2",{"path":1097,"priority":590},"references/example-event-taxonomy.md.j2",{"path":1099,"priority":590},"references/example-funnel-breakdown.md.j2",{"path":1101,"priority":590},"references/example-funnel-trends.md.j2",{"path":1103,"priority":590},"references/example-lifecycle.md.j2",{"path":1005,"priority":590},{"path":1007,"priority":590},{"path":1107,"priority":590},"references/example-logs.md.j2",{"path":1109,"priority":590},"references/example-paths.md.j2",{"path":1111,"priority":590},"references/example-person-property-taxonomy.md.j2",{"path":1113,"priority":590},"references/example-retention.md.j2",{"path":1115,"priority":590},"references/example-session-replay.md.j2",{"path":1117,"priority":590},"references/example-sessions.md.j2",{"path":1119,"priority":590},"references/example-stickiness.md.j2",{"path":1121,"priority":590},"references/example-team-taxonomy.md.j2",{"path":1123,"priority":590},"references/example-trends-breakdowns.md.j2",{"path":1125,"priority":590},"references/example-trends-unique-users.md.j2",{"path":1127,"priority":590},"references/example-web-overview.md.j2",{"path":1129,"priority":590},"references/example-web-path-stats.md.j2",{"path":1131,"priority":590},"references/example-web-traffic-by-device-type.md.j2",{"path":1133,"priority":590},"references/example-web-traffic-channels.md.j2",{"path":1135,"priority":590},"references/guidelines.md",{"path":1137,"priority":590},"references/hogql-extensions.md",{"path":1139,"priority":590},"references/models-actions.md",{"path":1141,"priority":590},"references/models-activity-logs.md",{"path":1143,"priority":590},"references/models-alerts.md",{"path":1145,"priority":590},"references/models-annotations.md",{"path":1147,"priority":590},"references/models-batch-exports.md",{"path":1149,"priority":590},"references/models-cohorts.md",{"path":1151,"priority":590},"references/models-dashboards-insights.md",{"path":1153,"priority":590},"references/models-data-warehouse.md",{"path":1155,"priority":590},"references/models-early-access-features.md",{"path":1157,"priority":590},"references/models-endpoints.md",{"path":1159,"priority":590},"references/models-error-tracking.md",{"path":1161,"priority":590},"references/models-flags-experiments.md",{"path":1163,"priority":590},"references/models-hog-flows.md",{"path":1165,"priority":590},"references/models-hog-functions.md",{"path":1167,"priority":590},"references/models-integrations.md",{"path":1169,"priority":590},"references/models-llm-analytics-reviews.md",{"path":1171,"priority":590},"references/models-logs.md",{"path":1173,"priority":590},"references/models-notebooks.md",{"path":1175,"priority":590},"references/models-session-recording-playlists.md",{"path":1177,"priority":590},"references/models-session-recordings.md",{"path":1179,"priority":590},"references/models-support-tickets.md",{"path":1181,"priority":590},"references/models-surveys.md",{"path":1183,"priority":590},"references/models-usage-metrics.md",{"path":1185,"priority":590},"references/models-variables.md",{"path":1187,"priority":590},"references/person-property-modes.md",{"path":1189,"priority":590},"references/taxonomy-dynamic-properties.md",{"path":1191,"priority":590},"references/taxonomy-skipped-events.md",{"basePath":1193,"description":1194,"displayName":1195,"installMethods":1196,"rationale":1197,"selectedPaths":1198,"source":272,"sourceLanguage":18,"type":247},"products/product_analytics/skills/exploring-autocapture-events","Guides exploration of $autocapture events captured by posthog-js to understand user interactions, find CSS selectors (especially data-attr attributes), evaluate selector uniqueness, query matching clicks ad-hoc, and create actions. Use when the user asks about autocapture data, wants to find what users are clicking, needs to build actions from click events, asks about elements_chain, wants to build a trend or funnel filtered by clicks or other autocapture interactions, asks which properties autocapture sends, or asks how to filter $autocapture events. Only applies to projects using posthog-js autocapture.\n","exploring-autocapture-events",{"claudeCode":12},"SKILL.md frontmatter at products/product_analytics/skills/exploring-autocapture-events/SKILL.md",[1199,1200,1202],{"path":587,"priority":271},{"path":1201,"priority":590},"references/elements-chain-format.md",{"path":1203,"priority":590},"references/example-queries.md",{"basePath":1205,"description":1206,"displayName":1207,"installMethods":1208,"rationale":1209,"selectedPaths":1210,"source":272,"sourceLanguage":18,"type":247},"products/product_analytics/skills/investigate-metric","Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries. Use when the user reports an anomaly, asks \"why did X change?\", or needs root-cause analysis for a trend, funnel, retention, stickiness, or lifecycle metric.\n","investigate-metric",{"claudeCode":12},"SKILL.md frontmatter at products/product_analytics/skills/investigate-metric/SKILL.md",[1211,1212,1214,1216,1218,1220,1222,1224,1226,1228,1230,1232],{"path":587,"priority":271},{"path":1213,"priority":590},"references/box-plot-playbook.md",{"path":1215,"priority":590},"references/common-causes.md",{"path":1217,"priority":590},"references/funnel-playbook.md",{"path":1219,"priority":590},"references/lifecycle-playbook.md",{"path":1221,"priority":590},"references/paths-playbook.md",{"path":1223,"priority":590},"references/retention-playbook.md",{"path":1225,"priority":590},"references/shared-patterns.md",{"path":1227,"priority":590},"references/stickiness-playbook.md",{"path":1229,"priority":590},"references/trend-playbook.md",{"path":1231,"priority":965},"scripts/breakdown_attribution.py",{"path":1233,"priority":965},"scripts/compare_to_prior_periods.py",{"basePath":1235,"description":1236,"displayName":1237,"installMethods":1238,"rationale":1239,"selectedPaths":1240,"source":272,"sourceLanguage":18,"type":247},"products/query_performance_ai/sandboxed_autoresearch_agent/pi_plugin/skills/clickhouse-autoresearch-campaign","Run a ClickHouse query optimization campaign on one git branch using pi-autoresearch, dynamic lanes and hypotheses, baseline result capture, correctness checks, and stagnation-aware lane/campaign review.","clickhouse-autoresearch-campaign",{"claudeCode":12},"SKILL.md frontmatter at products/query_performance_ai/sandboxed_autoresearch_agent/pi_plugin/skills/clickhouse-autoresearch-campaign/SKILL.md",[1241,1242],{"path":587,"priority":271},{"path":1243,"priority":590},"orchestration.md",{"basePath":1245,"description":1246,"displayName":1247,"installMethods":1248,"rationale":1249,"selectedPaths":1250,"source":272,"sourceLanguage":18,"type":247},"products/replay/skills/debugging-local-replay","Debugs why session recordings aren't appearing in the local dev environment. Use when a developer reports that local replay ingestion isn't working, recordings aren't showing up despite /s calls, or the replay pipeline seems broken after hogli start. Covers the full local pipeline: SDK capture, Caddy proxy, capture-replay (Rust), Kafka, ingestion-sessionreplay (Node), recording-api (Node), SeaweedFS, and common failure modes like orphaned processes, stuck phrocs workers, and trigger misconfiguration.\n","debugging-local-replay",{"claudeCode":12},"SKILL.md frontmatter at products/replay/skills/debugging-local-replay/SKILL.md",[1251,1252],{"path":587,"priority":271},{"path":1253,"priority":590},"references/common-failures.md",{"basePath":1255,"description":1256,"displayName":1257,"installMethods":1258,"rationale":1259,"selectedPaths":1260,"source":272,"sourceLanguage":18,"type":247},"products/replay/skills/diagnosing-missing-recordings","Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling, triggers, ad blockers, and quota/billing scenarios.\n","diagnosing-missing-recordings",{"claudeCode":12},"SKILL.md frontmatter at products/replay/skills/diagnosing-missing-recordings/SKILL.md",[1261,1262,1264,1266],{"path":587,"priority":271},{"path":1263,"priority":590},"references/diagnosis-logic.md",{"path":1265,"priority":590},"references/diagnostic-signals.md",{"path":1267,"priority":590},"references/examples.md",{"basePath":1269,"description":1270,"displayName":1271,"installMethods":1272,"rationale":1273,"selectedPaths":1274,"source":272,"sourceLanguage":18,"type":247},"products/replay/skills/finding-replay-for-issue","Finds the most informative session recording linked to an error tracking issue. Use when a user has an error tracking issue ID and wants to watch a replay showing what the user was doing when the error occurred. Ranks linked sessions by recency, activity score, and journey completeness, then summarizes the pre-error context. Replaces blind session picking from potentially hundreds of linked recordings.\n","finding-replay-for-issue",{"claudeCode":12},"SKILL.md frontmatter at products/replay/skills/finding-replay-for-issue/SKILL.md",[1275],{"path":587,"priority":271},{"basePath":1277,"description":1278,"displayName":1279,"installMethods":1280,"rationale":1281,"selectedPaths":1282,"source":272,"sourceLanguage":18,"type":247},"products/replay/skills/investigating-replay","Investigates a session recording by gathering metadata, person profile, same-session events, and linked error tracking issues in one pass. Use when a user provides a recording or session ID and wants to understand what happened — who the user was, what they did, what errors occurred, and whether there are related error tracking issues. Replaces the manual chain of session-recording-get, persons-retrieve, execute-sql, and query-error-tracking-issues-list.\n","investigating-replay",{"claudeCode":12},"SKILL.md frontmatter at products/replay/skills/investigating-replay/SKILL.md",[1283],{"path":587,"priority":271},{"basePath":1285,"description":1286,"displayName":1287,"installMethods":1288,"rationale":1289,"selectedPaths":1290,"source":272,"sourceLanguage":18,"type":247},"products/signals/skills/inbox-exploration","Explore PostHog's Inbox — the surface where signal reports surface as actionable issues and trends. Use when the user asks \"what's in my inbox?\", \"what should I look at?\", \"which reports are actionable?\", \"what's PostHog flagged recently?\", asks about a specific report by ID or title, or wants to see which signal sources are configured. Covers listing, filtering, and drilling into reports, plus pointers to the deeper `signals` skill when raw signals or semantic search are needed.\n","inbox-exploration",{"claudeCode":12},"SKILL.md frontmatter at products/signals/skills/inbox-exploration/SKILL.md",[1291],{"path":587,"priority":271},{"basePath":1293,"description":1294,"displayName":1295,"installMethods":1296,"rationale":1297,"selectedPaths":1298,"source":272,"sourceLanguage":18,"type":247},"products/signals/skills/signals","How to query the document_embeddings table for raw signal data using HogQL. Use when you need to perform semantic search over signals, fetch every signal that contributed to a specific report, or list signal types. For browsing the curated report layer (the Inbox) — listing reports, filtering by status/source, drilling into a single report by ID — use the `inbox-exploration` skill first; drop into this skill afterwards if the user wants the underlying observations.\n","signals",{"claudeCode":12},"SKILL.md frontmatter at products/signals/skills/signals/SKILL.md",[1299],{"path":587,"priority":271},{"basePath":1301,"description":1302,"displayName":1303,"installMethods":1304,"rationale":1305,"selectedPaths":1306,"source":272,"sourceLanguage":18,"type":247},"products/tracing/skills/exploring-apm-traces","Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP. Use when the user asks about service traces, slow HTTP/database spans, error spans, trace IDs, or span attributes — not LLM analytics traces or product logs. Uses posthog:query-apm-spans, posthog:apm-trace-get, posthog:apm-services-list, posthog:apm-attributes-list, and posthog:apm-attribute-values-list.\n","exploring-apm-traces",{"claudeCode":12},"SKILL.md frontmatter at products/tracing/skills/exploring-apm-traces/SKILL.md",[1307],{"path":587,"priority":271},{"basePath":1309,"description":1310,"displayName":1311,"installMethods":1312,"rationale":1313,"selectedPaths":1314,"source":272,"sourceLanguage":18,"type":247},"products/visual_review/skills/triaging-visual-review-runs","Inspects PostHog Visual Review (VR) runs that gate PR merges with screenshot regression checks. Use when the user mentions \"visual review\", \"VR\", \"snapshot diff\", \"screenshot test\", \"storybook regression\", \"playwright snapshot\", asks why a PR is blocked or what changed visually, wants to triage the VR backlog, decide whether a snapshot diff is real vs flaky, or check whether a story has been changing across runs. Also invoke when a PR has a failing `visual-review` status check, when a PR comment mentions \"Visual review\", or when the user is on a branch with an open VR run.\n","triaging-visual-review-runs",{"claudeCode":12},"SKILL.md frontmatter at products/visual_review/skills/triaging-visual-review-runs/SKILL.md",[1315],{"path":587,"priority":271},{"basePath":1317,"description":1318,"displayName":1319,"installMethods":1320,"rationale":1321,"selectedPaths":1322,"source":272,"sourceLanguage":18,"type":247},"products/web_analytics/skills/exploring-live-traffic","Inspects PostHog Web analytics Live tab data — current users online, last-30-minutes pageviews, top pages, referrers, devices, browsers, countries, bot traffic, and the per-minute bot/users charts. Use when the user asks \"who is on my site right now?\", \"what is happening live?\", \"what bots are crawling me?\", asks about the \"live tab\" / \"live dashboard\", wants live numbers (last 30 min), or wants help filtering or drilling into the live view. Also covers building product-analytics insights that mirror what the tiles show.","exploring-live-traffic",{"claudeCode":12},"SKILL.md frontmatter at products/web_analytics/skills/exploring-live-traffic/SKILL.md",[1323],{"path":587,"priority":271},{"basePath":1325,"description":1326,"displayName":1327,"installMethods":1328,"rationale":1329,"selectedPaths":1330,"source":272,"sourceLanguage":18,"type":247},"products/web_analytics/skills/managing-path-cleaning-rules","Inspects URL paths and proposes, tests, orders, and applies project-level path cleaning rules so dynamic segments (numeric IDs, UUIDs, slugs, dates) collapse into readable aliases. Use when the user says \"clean the paths\", \"normalize URLs\", \"group similar pages\", \"too many distinct paths\", \"/users/123 and /users/456 are the same page\", \"set up path cleaning\", or asks why a Web analytics or Paths breakdown is fragmented across thousands of nearly-identical URLs. Covers regex syntax (re2), alias placeholder convention, rule ordering, the test workflow, and applying rules via the project-settings-update MCP tool.","managing-path-cleaning-rules",{"claudeCode":12},"SKILL.md frontmatter at products/web_analytics/skills/managing-path-cleaning-rules/SKILL.md",[1331],{"path":587,"priority":271},{"basePath":1333,"description":1334,"displayName":1335,"installMethods":1336,"rationale":1337,"selectedPaths":1338,"source":272,"sourceLanguage":18,"type":247},"tools/traffic-sim/skills/check-posthog-loading","Inspect how the PostHog JavaScript SDK is loaded across a list of URLs. Use to confirm consistent installation across pages, find pages missing the snippet, detect mismatched API keys or hosts between pages, and verify the load method (head snippet vs deferred vs array.js).\n","check-posthog-loading",{"claudeCode":12},"SKILL.md frontmatter at tools/traffic-sim/skills/check-posthog-loading/SKILL.md",[1339],{"path":587,"priority":271},{"basePath":1341,"description":1342,"displayName":1343,"installMethods":1344,"rationale":1345,"selectedPaths":1346,"source":272,"sourceLanguage":18,"type":247},"tools/traffic-sim/skills/simulate-new-user","Send synthetic first-time-visitor traffic to a URL and confirm that PostHog $pageview events fire. Use when a customer wants to verify that anonymous visitor tracking works, after deploying instrumentation changes, or when debugging \"events not arriving\" reports.\n","simulate-new-user",{"claudeCode":12},"SKILL.md frontmatter at tools/traffic-sim/skills/simulate-new-user/SKILL.md",[1347],{"path":587,"priority":271},{"basePath":1349,"description":1350,"displayName":1351,"installMethods":1352,"rationale":1353,"selectedPaths":1354,"source":272,"sourceLanguage":18,"type":247},"tools/traffic-sim/skills/simulate-returning-user","Send synthetic single-session multi-page traffic to a URL and confirm PostHog $pageview events fire across page views. Use when verifying that cookies persist correctly, that the same distinct_id is reused across navigations, or when debugging session-stitching issues.\n","simulate-returning-user",{"claudeCode":12},"SKILL.md frontmatter at tools/traffic-sim/skills/simulate-returning-user/SKILL.md",[1355],{"path":587,"priority":271},{"basePath":1357,"description":1358,"displayName":1359,"installMethods":1360,"rationale":1361,"selectedPaths":1362,"source":272,"sourceLanguage":18,"type":247},"tools/traffic-sim/skills/verify-posthog-instrumentation","Use this skill to verify that PostHog instrumentation is firing correctly on a website. Drives a real browser at one or more URLs, observes which PostHog events actually arrive, and reports a pass/fail summary. Use after installing the PostHog SDK on a site, after a deploy that touches tracking code, or when events appear missing in the PostHog dashboard.\n","verify-posthog-instrumentation",{"claudeCode":12},"SKILL.md frontmatter at tools/traffic-sim/skills/verify-posthog-instrumentation/SKILL.md",[1363],{"path":587,"priority":271},{"basePath":1365,"displayName":1366,"installMethods":1367,"rationale":1368,"selectedPaths":1369,"source":272,"sourceLanguage":18,"type":1374},"products/visual_review/cli","@posthog/visual-review-cli",{"npm":1366},"cli ecosystem detected at products/visual_review/cli",[1370,1372],{"path":1371,"priority":271},"package.json",{"path":1373,"priority":965},"src/index.ts","cli",{"basePath":1376,"installMethods":1377,"rationale":1379,"selectedPaths":1380,"source":272,"sourceLanguage":18,"type":1374},"bin/hobby-installer",{"go":1378},"github.com/posthog/posthog/bin/hobby-installer","cli ecosystem detected at bin/hobby-installer",[1381,1383,1385],{"path":1382,"priority":271},"go.mod",{"path":1384,"priority":271},"README.md",{"path":1386,"priority":590},"main.go",{"basePath":1374,"installMethods":1388,"rationale":1390,"selectedPaths":1391,"source":272,"sourceLanguage":18,"type":1374},{"cargo":1389},"posthog-cli","cli ecosystem detected at cli",[1392,1394,1395,1397],{"path":1393,"priority":271},"Cargo.toml",{"path":1384,"priority":271},{"path":1396,"priority":590},"src/main.rs",{"path":1398,"priority":965},"src/lib.rs",{"basePath":1400,"installMethods":1401,"rationale":1403,"selectedPaths":1404,"source":272,"sourceLanguage":18,"type":1374},"funnel-udf",{"cargo":1402},"funnels","cli ecosystem detected at funnel-udf",[1405,1406,1407],{"path":1393,"priority":271},{"path":1384,"priority":271},{"path":1396,"priority":590},{"basePath":1409,"installMethods":1410,"rationale":1412,"selectedPaths":1413,"source":272,"sourceLanguage":18,"type":1374},"livestream",{"go":1411},"github.com/posthog/posthog/livestream","cli ecosystem detected at livestream",[1414,1415,1416],{"path":1382,"priority":271},{"path":1384,"priority":271},{"path":1386,"priority":590},{"basePath":1418,"installMethods":1419,"rationale":1421,"selectedPaths":1422,"source":272,"sourceLanguage":18,"type":1374},"rust/batch-import-worker",{"cargo":1420},"batch-import-worker","cli ecosystem detected at rust/batch-import-worker",[1423,1424,1425],{"path":1393,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1427,"installMethods":1428,"rationale":1430,"selectedPaths":1431,"source":272,"sourceLanguage":18,"type":1374},"rust/capture",{"cargo":1429},"capture","cli ecosystem detected at rust/capture",[1432,1433,1434],{"path":1393,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1436,"installMethods":1437,"rationale":1439,"selectedPaths":1440,"source":272,"sourceLanguage":18,"type":1374},"rust/capture-logs",{"cargo":1438},"capture-logs","cli ecosystem detected at rust/capture-logs",[1441,1442,1443,1444],{"path":1393,"priority":271},{"path":1384,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1446,"installMethods":1447,"rationale":1449,"selectedPaths":1450,"source":272,"sourceLanguage":18,"type":1374},"rust/common/hogvm",{"cargo":1448},"hogvm","cli ecosystem detected at rust/common/hogvm",[1451,1452],{"path":1393,"priority":271},{"path":1398,"priority":965},{"basePath":1454,"installMethods":1455,"rationale":1457,"selectedPaths":1458,"source":272,"sourceLanguage":18,"type":1374},"rust/cyclotron-janitor",{"cargo":1456},"cyclotron-janitor","cli ecosystem detected at rust/cyclotron-janitor",[1459,1460,1461],{"path":1393,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1463,"installMethods":1464,"rationale":1466,"selectedPaths":1467,"source":272,"sourceLanguage":18,"type":1374},"rust/cymbal",{"cargo":1465},"cymbal","cli ecosystem detected at rust/cymbal",[1468,1469,1470,1471],{"path":1393,"priority":271},{"path":1384,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1473,"installMethods":1474,"rationale":1476,"selectedPaths":1477,"source":272,"sourceLanguage":18,"type":1374},"rust/embedding-worker",{"cargo":1475},"embedding-worker","cli ecosystem detected at rust/embedding-worker",[1478,1479,1480],{"path":1393,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1482,"installMethods":1483,"rationale":1484,"selectedPaths":1485,"source":272,"sourceLanguage":18,"type":1374},"rust/feature-flags",{"cargo":217},"cli ecosystem detected at rust/feature-flags",[1486,1487,1488,1490,1491],{"path":1393,"priority":271},{"path":1384,"priority":271},{"path":1489,"priority":590},"src/bin/warm-flags-cache.rs",{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1493,"installMethods":1494,"rationale":1496,"selectedPaths":1497,"source":272,"sourceLanguage":18,"type":1374},"rust/flags-consumer",{"cargo":1495},"flags-consumer","cli ecosystem detected at rust/flags-consumer",[1498,1499,1500],{"path":1393,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1502,"installMethods":1503,"rationale":1505,"selectedPaths":1506,"source":272,"sourceLanguage":18,"type":1374},"rust/hypercache-server",{"cargo":1504},"hypercache-server","cli ecosystem detected at rust/hypercache-server",[1507,1508,1509],{"path":1393,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1511,"installMethods":1512,"rationale":1514,"selectedPaths":1515,"source":272,"sourceLanguage":18,"type":1374},"rust/ingestion-consumer",{"cargo":1513},"ingestion-consumer","cli ecosystem detected at rust/ingestion-consumer",[1516,1517,1518],{"path":1393,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1520,"installMethods":1521,"rationale":1523,"selectedPaths":1524,"source":272,"sourceLanguage":18,"type":1374},"rust/kafka-assigner",{"cargo":1522},"kafka-assigner","cli ecosystem detected at rust/kafka-assigner",[1525,1526,1527],{"path":1393,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1529,"installMethods":1530,"rationale":1532,"selectedPaths":1533,"source":272,"sourceLanguage":18,"type":1374},"rust/kafka-deduplicator",{"cargo":1531},"kafka-deduplicator","cli ecosystem detected at rust/kafka-deduplicator",[1534,1535,1536,1537],{"path":1393,"priority":271},{"path":1384,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1539,"installMethods":1540,"rationale":1542,"selectedPaths":1543,"source":272,"sourceLanguage":18,"type":1374},"rust/personhog-leader",{"cargo":1541},"personhog-leader","cli ecosystem detected at rust/personhog-leader",[1544,1545,1546,1547],{"path":1393,"priority":271},{"path":1384,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1549,"installMethods":1550,"rationale":1552,"selectedPaths":1553,"source":272,"sourceLanguage":1558,"type":1374},"rust/personhog-replica",{"cargo":1551},"personhog-replica","cli ecosystem detected at rust/personhog-replica",[1554,1555,1556,1557],{"path":1393,"priority":271},{"path":1384,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},"fr",{"basePath":1560,"installMethods":1561,"rationale":1563,"selectedPaths":1564,"source":272,"sourceLanguage":18,"type":1374},"rust/personhog-router",{"cargo":1562},"personhog-router","cli ecosystem detected at rust/personhog-router",[1565,1566,1567,1568],{"path":1393,"priority":271},{"path":1384,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1570,"installMethods":1571,"rationale":1573,"selectedPaths":1574,"source":272,"sourceLanguage":18,"type":1374},"rust/personhog-writer",{"cargo":1572},"personhog-writer","cli ecosystem detected at rust/personhog-writer",[1575,1576,1577,1578],{"path":1393,"priority":271},{"path":1384,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1580,"installMethods":1581,"rationale":1583,"selectedPaths":1584,"source":272,"sourceLanguage":18,"type":1374},"rust/property-defs-rs",{"cargo":1582},"property-defs-rs","cli ecosystem detected at rust/property-defs-rs",[1585,1586,1587,1588],{"path":1393,"priority":271},{"path":1384,"priority":271},{"path":1396,"priority":590},{"path":1398,"priority":965},{"basePath":1590,"installMethods":1591,"rationale":1592,"selectedPaths":1593,"source":272,"sourceLanguage":18,"type":1374},"tools/hogli",{"pypi":632},"cli ecosystem detected at tools/hogli",[1594,1596,1597,1600,1602],{"path":1595,"priority":271},"pyproject.toml",{"path":1384,"priority":271},{"path":1598,"priority":1599},"LICENSE","high",{"path":1601,"priority":590},"src/hogli/cli.py",{"path":1603,"priority":965},"src/hogli/__main__.py",{"basePath":1605,"installMethods":1606,"rationale":1608,"selectedPaths":1609,"source":272,"sourceLanguage":18,"type":1374},"tools/phrocs",{"go":1607},"github.com/posthog/posthog/phrocs","cli ecosystem detected at tools/phrocs",[1610,1611,1612],{"path":1382,"priority":271},{"path":1384,"priority":271},{"path":1386,"priority":590},{"sources":1614},[1615],"manual",{"npmPackage":1617},"@posthog/root",{"closedIssues90d":232,"description":1619,"forks":233,"homepage":1620,"license":239,"openIssues90d":234,"pushedAt":235,"readmeSize":230,"stars":236,"topics":1621},"🦔 PostHog is an all-in-one developer platform for building successful products. We offer product analytics, web analytics, session replay, error tracking, feature flags, experimentation, surveys, data warehouse, a CDP, and an AI product assistant to help debug your code, ship features faster, and keep all your usage and customer data in one stack.","https://posthog.com",[1622,1623,1624,1625,1626,214,213,217,1627,1628,1629,1630,215,1631,1632],"analytics","python","react","javascript","typescript","session-replay","ai-analytics","cdp","data-warehouse","surveys","web-analytics",{"downloads":8},{"classifiedAt":1635,"discoverAt":1636,"extractAt":1637,"githubAt":1637,"npmAt":1638,"updatedAt":1635},1778695659926,1778695623992,1778695651179,1778695654741,[214,213,217,216,215],{"evaluatedAt":243,"extractAt":1641,"updatedAt":243},1778695660274,[],[1644,1679,1697,1717,1744,1775],{"_creationTime":1645,"_id":1646,"community":1647,"display":1648,"identity":1654,"providers":1660,"relations":1671,"tags":1674,"workflow":1675},1778699093242.588,"k17bmad8esdm244kq3rwtmm9ms86nnyc",{"reviewCount":8},{"description":1649,"installMethods":1650,"name":1652,"sourceUrl":1653},"A/B-Tests und Funktionsoptimierung für KI-Agenten. Wählen Sie automatisch die beste Option mit Multi-Armed Bandits und kontextbezogenen Bandits (LinUCB). Kein Data Warehouse erforderlich – funktioniert ab der Anfrage.",{"claudeCode":1651},"Whatsonyourmind/oraclaw","OraClaw Bandit","https://github.com/Whatsonyourmind/oraclaw",{"basePath":1655,"githubOwner":1656,"githubRepo":1657,"locale":1658,"slug":1659,"type":247},"mission-control/packages/clawhub-skills/oraclaw-bandit","Whatsonyourmind","oraclaw","de","oraclaw-bandit",{"evaluate":1661,"extract":1669},{"promptVersionExtension":206,"promptVersionScoring":207,"score":1662,"tags":1663,"targetMarket":218,"tier":1668},99,[1664,214,217,1665,1666,1667],"optimization","experimentation","machine-learning","mcp","verified",{"commitSha":253,"license":1670},"MIT",{"repoId":1672,"translatedFrom":1673},"kd76fmxm1ng903s4fmj0p7hxxs86ndkg","k17ewnzxwqzf8m1b1t3c7srke186nx9a",[214,1665,217,1666,1667,1664],{"evaluatedAt":1676,"extractAt":1677,"updatedAt":1678},1778698869396,1778698837670,1778699093242,{"_creationTime":1680,"_id":1681,"community":1682,"display":1683,"identity":1685,"providers":1686,"relations":1693,"tags":1694,"workflow":1695},1778695660274.5066,"k17e9e13hdn15fttw4mh7jb10186nhjh",{"reviewCount":8},{"description":941,"installMethods":1684,"name":942,"sourceUrl":14},{"claudeCode":12},{"basePath":940,"githubOwner":246,"githubRepo":216,"locale":18,"slug":942,"type":247},{"evaluate":1687,"extract":1692},{"promptVersionExtension":206,"promptVersionScoring":207,"score":1688,"tags":1689,"targetMarket":218,"tier":1668},95,[216,217,1690,1691],"ci-cd","automation",{"commitSha":253},{"repoId":255},[1691,1690,217,216],{"evaluatedAt":1696,"extractAt":1641,"updatedAt":1696},1778697148525,{"_creationTime":1698,"_id":1699,"community":1700,"display":1701,"identity":1704,"providers":1705,"relations":1713,"tags":1714,"workflow":1715},1778695660274.506,"k177ate2v49febw3emka0zeb9186n7yd",{"reviewCount":8},{"description":925,"installMethods":1702,"name":1703,"sourceUrl":14},{"claudeCode":12},"Managing Experiment Lifecycle",{"basePath":924,"githubOwner":246,"githubRepo":216,"locale":18,"slug":926,"type":247},{"evaluate":1706,"extract":1711},{"promptVersionExtension":206,"promptVersionScoring":207,"score":1707,"tags":1708,"targetMarket":218,"tier":219},93,[1665,1709,217,1710,216],"a-b-testing","product-management",{"commitSha":253,"license":1712},"MIT-0",{"repoId":255},[1709,1665,217,216,1710],{"evaluatedAt":1716,"extractAt":1641,"updatedAt":1716},1778697110075,{"_creationTime":1718,"_id":1719,"community":1720,"display":1721,"identity":1727,"providers":1731,"relations":1737,"tags":1740,"workflow":1741},1778695720086.7703,"k176r34g5a5fjn1z1a4gq6v88186nje0",{"reviewCount":8},{"description":1722,"installMethods":1723,"name":1725,"sourceUrl":1726},"Designs an A/B test or experiment with clear hypothesis, variants, success metrics, sample size, and duration. Use when planning experiments to validate product changes or test hypotheses.",{"claudeCode":1724},"product-on-purpose/pm-skills","measure-experiment-design","https://github.com/product-on-purpose/pm-skills",{"basePath":1728,"githubOwner":1729,"githubRepo":1730,"locale":18,"slug":1725,"type":247},"skills/measure-experiment-design","product-on-purpose","pm-skills",{"evaluate":1732,"extract":1736},{"promptVersionExtension":206,"promptVersionScoring":207,"score":1733,"tags":1734,"targetMarket":218,"tier":1668},100,[214,1665,1710,1709,1735],"data-analysis",{"commitSha":253},{"parentExtensionId":1738,"repoId":1739},"k1721116hsfj7zg78w03432n8986n6y8","kd78ksv1wjj826ds5j1sh2kqnx86mhqf",[1709,214,1735,1665,1710],{"evaluatedAt":1742,"extractAt":1743,"updatedAt":1742},1778696438706,1778695720086,{"_creationTime":1745,"_id":1746,"community":1747,"display":1748,"identity":1754,"providers":1759,"relations":1768,"tags":1771,"workflow":1772},1778693180473.1133,"k17d2y3yt9d20wck91k38bs7s586ne6z",{"reviewCount":8},{"description":1749,"installMethods":1750,"name":1752,"sourceUrl":1753},"Azure App Configuration SDK for Python. Use for centralized configuration management, feature flags, and dynamic settings.\nTriggers: \"azure-appconfiguration\", \"AzureAppConfigurationClient\", \"feature flags\", \"configuration\", \"key-value settings\".\n",{"claudeCode":1751},"microsoft/agent-skills","Azure App Configuration SDK for Python","https://github.com/microsoft/agent-skills",{"basePath":1755,"githubOwner":1756,"githubRepo":1757,"locale":18,"slug":1758,"type":247},".github/plugins/azure-sdk-python/skills/azure-appconfiguration-py","microsoft","agent-skills","azure-appconfiguration-py",{"evaluate":1760,"extract":1767},{"promptVersionExtension":206,"promptVersionScoring":207,"score":1733,"tags":1761,"targetMarket":218,"tier":1668},[1762,1763,1764,1623,1765,217,1766],"azure","app-configuration","sdk","settings","devops",{"commitSha":253,"license":1670},{"parentExtensionId":1769,"repoId":1770},"k171mfx6atvhq1bkhpky84v4b186n9qd","kd77czgnv00rfjm815pcc5xx5986n5t8",[1763,1762,1766,217,1623,1764,1765],{"evaluatedAt":1773,"extractAt":1774,"updatedAt":1773},1778694802107,1778693180473,{"_creationTime":1776,"_id":1777,"community":1778,"display":1779,"identity":1785,"providers":1789,"relations":1795,"tags":1798,"workflow":1799},1778675056600.2664,"k173ggr45da0wr1c32bva99bvh86nj5a",{"reviewCount":8},{"description":1780,"installMethods":1781,"name":1783,"sourceUrl":1784},"Use when planning product experiments, writing testable hypotheses, estimating sample size, prioritizing tests, or interpreting A/B outcomes with practical statistical rigor.",{"claudeCode":1782},"alirezarezvani/claude-skills","experiment-designer","https://github.com/alirezarezvani/claude-skills",{"basePath":1786,"githubOwner":1787,"githubRepo":1788,"locale":18,"slug":1783,"type":247},"product-team/skills/experiment-designer","alirezarezvani","claude-skills",{"evaluate":1790,"extract":1794},{"promptVersionExtension":206,"promptVersionScoring":207,"score":1662,"tags":1791,"targetMarket":218,"tier":1668},[1665,214,1710,1792,1735,1793],"statistics","hypothesis-testing",{"commitSha":253},{"parentExtensionId":1796,"repoId":1797},"k17104ysr0smp7vvp26mnn1fzh86nynm","kd7ff9s1w43mfyy1n7hf87816186m6px",[214,1735,1665,1793,1710,1792],{"evaluatedAt":1800,"extractAt":1801,"updatedAt":1800},1778685452060,1778675056600]